I don't see it as a flaw.  It knows William's location and responds accordingly while also trying to response to the prompt.

I think your prompt depends on the type of AI you are using.  No need to ask for an image with Gencraft where as it would be quicker to ask for an image with Bing Chat.  Learning how to prompt an AI for best results is the learning curve we are experiencing now. 

The trick for generative AI is to learn how to best respond to humans despite human failings in spelling, grammar and muddled communication.  The AI is like a mother trying to understand her baby as it learns to talk. As the baby learns, the mother can better respond. 

AI is much much smarter than we are but it is built to respond.  It does nothing on its own.  It needs a prompt to do anything.  The better the prompt, the more useful the results to us.  It's a learning curve for us.

William, I had the same problem.  It was difficult to make Bing Chat produce a woman gondolier. I eventually got a female, but it took some doing.  Too exhausting to show you all the various prompts and results. Just know that you are not alone when it comes to female gondoliers failing to appear.  One reason may be that female gondoliers are very very rare.  But of course, that's no excuse when creating a work of art.

Quite right. AI image creation is rapidly being adopted.  It's faster and cheaper than humans and I agree many will lose their livelihood as AI keeps improving.  Bing Chat uses Dalle E3 to make images.  I asked Bing Chat how Dalle E3 works and especially could Dalle E3 provide a list of sources for the images it creates.   I got this answer. 

DALL-E 3 is an AI model that can create images based on natural language inputs, such as “teddy bears shopping for groceries in the style of Ukiyo-e”. It uses a large neural network that has been trained on a huge amount of text and images from the internet, so it can understand the meaning and context of the words and phrases that you provide, and generate images that match your description.

However, DALL-E 3 does not provide a list of sources for the images it creates, because it does not copy or reproduce any existing images. Instead, it synthesizes new images from scratch, based on its learned knowledge and creativity. Therefore, the images that DALL-E 3 creates are original and unique, and do not belong to any specific source or author.

Of course, this also means that DALL-E 3 might be influenced by the data that it has seen during its training, and might generate images that resemble or reference some existing works or styles. For example, DALL-E 3 can generate images in the style of a living artist, such as Picasso, but it will not generate an exact replica of any of Picasso’s paintings. In such cases, DALL-E 3 is designed to decline requests that ask for an image in the style of a living artist, to respect their intellectual property rights and artistic expression.

Are you using the latest version of Microsoft Edge to run the Bing?

I used this prompt with Bing: can you create an image to visualize the following sentence in welsh "Mae rhif ffôn Megan yn y swyddfa"

Got this image.

>>  but the images are not full field to some extent,

I'm getting 1024 x 1024.  I don't know what you mean by "images are not full field"?

I was able to limit the inks to two but I'm not sure how linocuts work.  Do they mix colors so that two inks create more than two colors?

Here's my first prompt:  create an image in the style of a linocut print of a landscape with a tree in the foreground.  Limit the colors to two inks.

Then I ask Bing to add the lady with the lute.

I had never heard the term linocut or forgotten it, but I imagine I've seen some somewhere.  This kind of thing amazes me that people can be so skilled to create images in this fashion. 

Looks like you were ahead of your time.   Free to the end user distance education has arrived, although I'm not sure about what you meant by the term "distance education".  Still your idea was prescient.  I'll read some of it as time permits.

I suppose that's the best system, advertiser supported services.  Personally, I can't stand the ads, so for YouTube, I pay to avoid them.  Worth it to me.  YouTube interruptions are arbitrary and altogether egregious. 

For now, the ad content in Bing's A.I. is not too bad and I can stand it. I notice in the Bing Chat there is a way to earn Microsoft Reward points. You get 50 points for using Bing to search on a particular day.  I'm not sure how that works.  Likely this will be the way to pay for an ad free Bing Chat.  Right now I'm not sure there is a way to avoid the ads.  I haven't seen anymore lately. Que sera, sera.

Bing Chat is altogether amazing.  It's a definite challenge to Google's dominance in "search".  Google has yet to respond with their own AI driven search.  Or have they, and I didn't notice?

Wow. I just learned things about the clipboard I never knew.  I'm running Windows 10 -- and wow .. clipboard is much more powerful than I knew about.

I"m always learning new things on Alfred's forum!